Tumor integrin targeted theranostic iron oxide nanoparticles for delivery of caffeic acid phenethyl ester: preparation, characterization, and anti-myeloma activities.

Multiple myeloma (MM) is characterized by the accumulation of malignant plasma cells preferentially in the bone marrow. Currently, emerging chemotherapy drugs with improved biosafety profiles, such as immunomodulatory agents and protease inhibitors, have been used in clinics to treat MM in both initial therapy or maintenance therapy post autologous hematopoietic stem cell transplantation (ASCT). We previously discovered that caffeic acid phenethyl ester (CAPE), a water-insoluble natural compound, inhibited the growth of MM cells by inducing oxidative stress. As part of our continuous effort to pursue a less toxic yet more effective therapeutic approach for MM, the objective of this study is to investigate the potential of CAPE for in vivo applications by using magnetic resonance imaging (MRI)-capable superparamagnetic iron oxide nanoparticles (IONP) as carriers. Cyclo (Arg-Gly-Asp-D-Phe-Cys) (RGD) is conjugated to IONP (RGD-IONP/CAPE) to target the overexpressed αvß3 integrin on MM cells for receptor-mediated internalization and intracellular delivery of CAPE. A stable loading of CAPE on IONP can be achieved with a loading efficiency of 48.7% ± 3.3% (wt%). The drug-release studies indicate RGD-IONP/CAPE is stable at physiological (pH 7.4) and basic pH (pH 9.5) and subject to release of CAPE at acidic pH (pH 5.5) mimicking the tumor and lysosomal condition. RGD-IONP/CAPE causes cytotoxicity specific to human MM RPMI8226, U266, and NCI-H929 cells, but not to normal peripheral blood mononuclear cells (PBMCs), with IC50s of 7.97 ± 1.39, 16.75 ± 1.62, and 24.38 ± 1.71 µM after 72-h treatment, respectively. Apoptosis assays indicate RGD-IONP/CAPE induces apoptosis of RPMI8226 cells through a caspase-9 mediated intrinsic pathway, the same as applying CAPE alone. The apoptogenic effect of RGD-IONP/CAPE was also confirmed on the RPMI8226 cells co-cultured with human bone marrow stromal cells HS-5 in a Transwell model to mimic the MM microenvironment in the bone marrow. In conclusion, we demonstrate that water-insoluble CAPE can be loaded to RGD-IONP to greatly improve the biocompatibility and significantly inhibit the growth of MM cells in vitro through the induction of apoptosis. This study paves the way for investigating the MRI-trackable delivery of CAPE for MM treatment in animal models in the future.

Arf1 Ablation in Colorectal Cancer Cells Activates a Super Signal Complex in DC to Enhance Anti-Tumor Immunity.

The anti-tumor immune response relies on interactions among tumor cells and immune cells. However, the molecular mechanisms by which tumor cells regulate DCs as well as DCs regulate T cells remain enigmatic. Here, the authors identify a super signaling complex in DCs that mediates the Arf1-ablation-induced anti-tumor immunity. They find that the Arf1-ablated tumor cells release OxLDL, HMGB1, and genomic DNA, which together bound to a coreceptor complex of CD36/TLR2/TLR6 on DC surface. The complex then is internalized into the Rab7-marked endosome in DCs, and further joined by components of the NF-κB, NLRP3 inflammasome and cGAS-STING triple pathways to form a super signal complex for producing different cytokines, which together promote CD8+ T cell tumor infiltration, cross-priming and stemness. Blockage of the HMGB1-gDNA complex or reducing expression in each member of the coreceptors or the cGAS/STING pathway prevents production of the cytokines. Moreover, depletion of the type I IFNs and IL-1ß cytokines abrogate tumor regression in mice bearing the Arf1-ablated tumor cells. These findings reveal a new molecular mechanism by which dying tumor cells releasing several factors to activate the triple pathways in DC for producing multiple cytokines to simultaneously promote DC activation, T cell infiltration, cross-priming and stemness.

Development and validation of machine learning models for venous thromboembolism risk assessment at admission: a retrospective study.

Introduction: Venous thromboembolism (VTE) risk assessment at admission is of great importance for early screening and timely prophylaxis and management during hospitalization. The purpose of this study is to develop and validate novel risk assessment models at admission based on machine learning (ML) methods. Methods: In this retrospective study, a total of 3078 individuals were included with their Caprini variables within 24 hours at admission. Then several ML models were built, including logistic regression (LR), random forest (RF), and extreme gradient boosting (XGB). The prediction performance of ML models and the Caprini risk score (CRS) was then validated and compared through a series of evaluation metrics. Results: The values of AUROC and AUPRC were 0.798 and 0.303 for LR, 0.804 and 0.360 for RF, and 0.796 and 0.352 for XGB, respectively, which outperformed CRS significantly (0.714 and 0.180, P < 0.001). When prediction scores were stratified into three risk levels for application, RF could obtain more reasonable results than CRS, including smaller false positive alerts and larger lower-risk proportions. The boosting results of stratification were further verified by the net-reclassification-improvement (NRI) analysis. Discussion: This study indicated that machine learning models could improve VTE risk prediction at admission compared with CRS. Among the ML models, RF was found to have superior performance and great potential in clinical practice.

A gradient boosting tree model for multi-department venous thromboembolism risk assessment with imbalanced data.

Venous thromboembolism (VTE) is the world's third most common cause of vascular mortality and a serious complication from multiple departments. Risk assessment of VTE guides clinical intervention in time and is of great importance to in-hospital patients. Traditional VTE risk assessment methods based on scaling tools, which always require rules carefully designed by human experts, are difficult to apply to large-population scenarios since the manually designed rules are not guaranteed to be accurate to all populations. In contrast, with the development of the electronic health record (EHR) datasets, data-driven machine-learning-based risk assessment methods have proven superior predictability in many studies in recent years. This paper uses the gradient boosting tree model to study the VTE risk assessment problem with multi-department data. There exist two distinct characteristics of VTE data collected at the level of the entire hospital: its wide distribution and heterogeneity across multiple departments. To this end, we consider the prediction task over multiple departments as a multi-task learning process, and introduce the algorithm of a task-aware tree-based method TSGB to tackle the multi-task prediction problem. Although the introduction of multi-task learning improves overall across-department performance, we reveal the problem of task-wise performance decline while dealing with imbalanced VTE data volume. According to the analysis, we finally propose two variants of TSGB to alleviate the problems and further boost the prediction performance. Compared with state-of-the-art rule-based and multi-task tree-based methods, the experimental results show the proposed methods not only improve the overall across-department AUC performance effectively, but also ensure the improvement of performance over every single department prediction.

Deep Unsupervised Active Learning on Learnable Graphs.

Recently, deep learning has been successfully applied to unsupervised active learning. However, the current method attempts to learn a nonlinear transformation via an auto-encoder while ignoring the sample relation, leaving huge room to design more effective representation learning mechanisms for unsupervised active learning. In this brief, we propose a novel deep unsupervised active learning model via learnable graphs, named ALLGs. ALLG benefits from learning optimal graph structures to acquire better sample representation and select representative samples. To make the learned graph structure more stable and effective, we take into account k -nearest neighbor graph as a priori and learn a relation propagation graph structure. We also incorporate shortcut connections among different layers, which can alleviate the well-known over-smoothing problem to some extent. To the best of our knowledge, this is the first attempt to leverage graph structure learning for unsupervised active learning. Extensive experiments performed on six datasets demonstrate the efficacy of our method.

Structure Guided Deep Neural Network for Unsupervised Active Learning.

Unsupervised active learning has become an active research topic in the machine learning and computer vision communities, whose goal is to choose a subset of representative samples to be labeled in an unsupervised setting. Most of existing approaches rely on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of the selected samples, and then take these selected samples as the representative ones for manual labeling. However, the data do not necessarily conform to the linear models in many real-world scenarios, and how to model nonlinearity of data often becomes the key point of unsupervised active learning. Moreover, the existing works often aim to well reconstruct the whole dataset, while ignore the important cluster structure, especially for imbalanced data. In this paper, we present a novel deep unsupervised active learning framework. The proposed method can explicitly learn a nonlinear embedding to map each input into a latent space via a deep neural network, and introduce a selection block to select the representative samples in the learnt latent space through a self-supervised learning strategy. In the selection block, we aim to not only preserve the global structure of the data, but also capture the cluster structure of the data in order to well handle the data imbalance issue during sample selection. Meanwhile, we take advantage of the clustering result to provide self-supervised information to guide the above processes. Finally, we attempt to preserve the local structure of the data, such that the data embedding becomes more precise and the model performance can be further improved. Extensive experimental results on several publicly available datasets clearly demonstrate the effectiveness of our method, compared with the state-of-the-arts.

A novel hierarchical machine learning model for hospital-acquired venous thromboembolism risk assessment among multiple-departments.

Venous thromboembolism (VTE) is a common vascular disease and potentially fatal complication during hospitalization, and so the early identification of VTE risk is of significant importance. Compared with traditional scale assessments, machine learning methods provide new opportunities for precise early warning of VTE from clinical medical records. This research aimed to propose a two-stage hierarchical machine learning model for VTE risk prediction in patients from multiple departments. First, we built a machine learning prediction model that covered the entire hospital, based on all cohorts and common risk factors. Then, we took the prediction output of the first stage as an initial assessment score and then built specific models for each department. Over the duration of the study, a total of 9213 inpatients, including 1165 VTE-positive samples, were collected from four departments, which were split into developing and test datasets. The proposed model achieved an AUC of 0.879 in the department of oncology, which outperformed the first-stage model (0.730) and the department model (0.787). This was attributed to the fully usage of both the large sample size at the hospital level and variable abundance at the department level. Experimental results show that our model could effectively improve the prediction of hospital-acquired VTE risk before image diagnosis and provide decision support for further nursing and medical intervention.

Anti-osteoporosis medication treatment pattern after osteoporotic fracture during 2010-2016 in Fujian, China.

This study demonstrates a low anti-osteoporosis drug treatment rate (22.1% in women, 9.5% in men) after osteoporotic fracture in the real-world setting of Fujian, China. The primary medication was calcitonin. The suboptimal treatment was particularly critical among men, low-level hospitals, wrist/vertebral fracture, and the younger elderly patients. INTRODUCTION: The objective of this study was to investigate the prescription patterns and related influencing factors of anti-osteoporosis drug prescribing after osteoporotic fracture in Fujian, China, between 2010 and 2016. METHODS: This is a retrospective cohort study based on an existing electronic health record database (National Healthcare Big Data in Fuzhou, China, 37 hospitals included). Patients over 50 years old with newly diagnosed osteoporotic fractures between 2010 and 2016 were included. Postfracture osteoporosis therapies were summarized by overall and fracture site. Multivariate logistic regression was performed to identify influencing factors of anti-osteoporosis medication (AOM) prescription. RESULTS: Overall, 22.1% of women and 9.5% of men over 50 years old received AOM treatment after osteoporotic fracture within 1 year during 2010-2016, with particular low use of bisphosphonates, 5.3% in women and 1.5% in men. The highest rate of AOM treatment was found in patients with hip fracture (24.5%), followed by vertebral fracture (14.2%) and wrist fracture (2.3%). Of the AOM-treated patients, 90.5% received calcitonin therapy. The treatment rate of AOM showed a slight decline during 2010-2016, but steady rise trends were observed in Ca/vitamin D (VD) prescription. Hospital level, age, sex, previous osteoporosis, previous AOM prescription, and previous oral glucocorticoid prescription were strong predicting factors of AOM prescription. CONCLUSION: In a real-world setting, AOM treatment was suboptimal and the treatment rate even decreased over time among osteoporosis fracture patients in Fujian, China. The suboptimal treatment was particularly critical among men, low-level hospitals, wrist/vertebral fracture, and the younger elderly patients.

Growth inhibition and apoptosis of human multiple myeloma cells induced by 2-cyano-3,12-dioxooleana-1,9-dien-28-oic acid derivatives.

Multiple myeloma is a blood cell cancer and can cause symptoms such as bone loss and fatigue. Recent studies have shown that the bone marrow microenvironment may mediate tumor proliferation, drug resistance, and migration of the multiple myeloma cells. Synthetic triterpenoids have been used for the treatment of cancer due to their antiproliferative and anti-inflammatory effects. The objective of this study is to examine the effect of 2-cyano-3, 12 dioxoolean-1,9-dien-28-oic acid (CDDO) derivatives on human multiple myeloma cells. Three CDDO derivatives, such as CDDO-methyl ester, CDDO-trifluroethyl amide, and CDDO-imidazolide (Im), were tested on the growth of human multiple myeloma cells. Our results show that all CDDO derivatives decrease the viability of multiple myeloma cells in a dose- and time-dependent manner, with CDDO-Im being the most potent. CDDO-Im was selected to investigate whether its inhibitory effect on multiple myeloma cell growth is due to cell cycle arrest and induction of apoptosis. The results suggest that CDDO-Im may inhibit cell cycle progression in the G0/G1 phase and induce the intrinsic apoptotic pathway. The effect of CDDO-Im on multiple myeloma cells was evaluated in a Transwell model using myeloma cells co-culturing with human HS-5 stromal cells to simulate the bone marrow microenvironment in vitro. The results showed that CDDO-Im induced multiple myeloma cell apoptosis in the presence of HS-5 cells, albeit to a lower extent than in multiple myeloma cells cultured alone. In conclusion, our data suggest that CDDO-Im inhibits the growth of multiple myeloma cells, either cultured alone or co-cultured with bone marrow stromal cells, through the induction of apoptosis.

Epidemiology of Febrile Neutropenia Episodes with Gram-Negative Bacteria Infection in Patients Who Have Undergone Chemotherapy for Hematologic Malignancies: A Retrospective Study of 10 Years' Data from a Single Center.

BACKGROUND: The epidemiology of Gram-negative bacteria in patients with febrile neutropenia (FN) and their susceptibility to initial empirical antibiotic therapy is key to successful treatment during the treatment of hematologic malignancies. METHODS: A retrospective study was conducted. Patients with FN and confirmed laboratory results of Gram-negative bacteria infections were included. If no direct sensitivity of the identified pathogen to the initially prescribed antibiotic regimen was confirmed, it was defined as inappropriate initial antibiotic treatment (IIAT). RESULTS: A total of 247 patients with FN were proven to be infected with Gram-negative bacteria, and 200 were diagnosed with acute leukemia. The most commonly detected bacteria were Escherichia coli (40%), Klebsiella pneumoniae (20%), and Pseudomonas aeruginosa (11%). In sum, 176 patients were classified as IIAT. The mortality rate in the IIAT group was significantly higher (37.7% vs 23.9%, P=0.038). With monotherapy as empirical treatment, high possibility of IIAT with fluoroquinolones (52%) and cephalosporins (35%) was detected, while more sensitivity to carbapenems (16%) and glycopeptides antibiotics (19%) was noticed. With combined treatment, cephalosporins/carbapenems had with the lowest percentage of IIAT (18%). CONCLUSION: In conclusion, inappropriate initial empirical antibiotic treatments were associated with higher mortality in patients with hematologic malignancies. The current empirical antibiotic regimen needs to be further optimized.

Periostin Promotes Colorectal Tumorigenesis through Integrin-FAK-Src Pathway-Mediated YAP/TAZ Activation.

Periostin is a multifunctional extracellular matrix protein involved in various inflammatory diseases and tumor metastasis; however, evidence regarding whether and how periostin actively contributes to inflammation-associated tumorigenesis remains elusive. Here, we demonstrate that periostin deficiency significantly inhibits the occurrence of colorectal cancer in azoxymethane/dextran sulfate sodium-treated mice and in ApcMin/+ mice. Moreover, periostin deficiency attenuates the severity of colitis and reduces the proliferation of tumor cells. Mechanistically, stromal fibroblast-derived periostin activates FAK-Src kinases through integrin-mediated outside-in signaling, which results in the activation of YAP/TAZ and, subsequently, IL-6 expression in tumor cells. Conversely, IL-6 induces periostin expression in fibroblasts by activating STAT3, which ultimately facilitates colorectal tumor development. These findings provide the evidence that periostin promotes colorectal tumorigenesis, and identify periostin- and IL-6-mediated tumor-stroma interaction as a promising target for treating colitis-associated colorectal cancer.

Lipid-Lowering Therapy and Low-Density Lipoprotein Cholesterol (LDL-C) Goal Achievement in High-Cardiovascular-Risk Patients in Fuzhou, China.

PURPOSE: This study aims to analyze the treatment patterns and goal attainment of low-density lipoprotein cholesterol (LDL-C) among patients with atherosclerotic cardiovascular disease (ASCVD) and diabetes mellitus (DM) in the real-world setting in Fuzhou, China. METHODS: Patients aged ≥20 years with a valid LDL-C measurement (index date) in 2016 were selected from National Healthcare Big Data in Fuzhou, China. Patients were stratified into mutually exclusive cardiovascular risk categories: ASCVD (including recent acute coronary syndrome [ACS], chronic coronary heart disease [CHD], stroke, and peripheral arterial disease [PAD]), and DM alone (without ASCVD). Lipid-modifying medication and LDL-C attainment at the index date were assessed. RESULTS: A total of 21 989 patients met the inclusion criteria, including 17 320 (78.8%) with ASCVD and 4669 (21.2%) with DM alone; 47.7% of patients received current statin therapy in the overall cohort (53.5% in ASCVD, 26.5% for DM); 20.5% ASCVD population achieved LDL-C target with the highest in patients with recent ACS (33.8%), followed by chronic CHD (21.2%), PAD (20.9%), and ischemic stroke (17.3%); 49.0% of patients with DM achieved LDL-C target. Higher LDL-C attainment was observed in high-intensity statin and a combination of statin and nonstatin groups. Atorvastatin was the most commonly used statin with the highest LDL-C attainment, followed by rosuvastatin. CONCLUSION: Compared with previous studies in China, our study found a relatively low statin use and LDL-C target attainment, but higher than similar studies in Europe. Guidelines should be well complied and more prescription of high-intensity statin or statin and nonstatin combination should be advocated.

Development and Validation of a Machine Learning Prognostic Model for Hepatocellular Carcinoma Recurrence After Surgical Resection.

Surgical resection remains primary curative treatment for patients with hepatocellular carcinoma (HCC) while over 50% of patients experience recurrence, which calls for individualized recurrence prediction and early surveillance. This study aimed to develop a machine learning prognostic model to identify high-risk patients after surgical resection and to review importance of variables in different time intervals. The patients in this study were from two centers including Eastern Hepatobiliary Surgery Hospital (EHSH) and Mengchao Hepatobiliary Hospital (MHH). The best-performed model was determined, validated, and applied to each time interval (0-1 year, 1-2 years, 2-3 years, and 3-5 years). Importance scores were used to illustrate feature importance in different time intervals. In addition, a risk heat map was constructed which visually depicted the risk of recurrence in different years. A total of 7,919 patients from two centers were included, of which 3,359 and 230 patients experienced recurrence, metastasis or died during the follow-up time in the EHSH and MHH datasets, respectively. The XGBoost model achieved the best discrimination with a c-index of 0.713 in internal validation cohort. Kaplan-Meier curves succeed to stratify external validation cohort into different risk groups (p < 0.05 in all comparisons). Tumor characteristics contribute more to HCC relapse in 0 to 1 year while HBV infection and smoking affect patients' outcome largely in 3 to 5 years. Based on machine learning prediction model, the peak of recurrence can be predicted for individual HCC patients. Therefore, clinicians can apply it to personalize the management of postoperative survival.

Detection of medical text semantic similarity based on convolutional neural network.

BACKGROUND: Imaging examinations, such as ultrasonography, magnetic resonance imaging and computed tomography scans, play key roles in healthcare settings. To assess and improve the quality of imaging diagnosis, we need to manually find and compare the pre-existing reports of imaging and pathology examinations which contain overlapping exam body sites from electrical medical records (EMRs). The process of retrieving those reports is time-consuming. In this paper, we propose a convolutional neural network (CNN) based method which can better utilize semantic information contained in report texts to accelerate the retrieving process. METHODS: We included 16,354 imaging and pathology report-pairs from 1926 patients who admitted to Shanghai Tongren Hospital and had ultrasonic examinations between 1st May 2017 and 31st July 2017. We adapted the CNN model to calculate the similarities among the report-pairs to identify target report-pairs with overlapping body sites, and compared the performance with other six conventional models, including keyword mapping, latent semantic analysis (LSA), latent Dirichlet allocation (LDA), Doc2Vec, Siamese long short term memory (LSTM) and a model based on named entity recognition (NER). We also utilized graph embedding method to enhance the word representation by capturing the semantic relations information from medical ontologies. Additionally, we used LIME algorithm to identify which features (or words) are decisive for the prediction results and improved the model interpretability. RESULTS: Experiment results showed that our CNN model gained significant improvement compared to all other conventional models on area under the receiver operating characteristic (AUROC), precision, recall and F1-score in our test dataset. The AUROC of our CNN models gained approximately 3-7% improvement. The AUROC of CNN model with graph-embedding and ontology based medical concept vectors was 0.8% higher than the model with randomly initialized vectors and 1.5% higher than the one with pre-trained word vectors. CONCLUSION: Our study demonstrates that CNN model with pre-trained medical concept vectors could accurately identify target report-pairs with overlapping body sites and potentially accelerate the retrieving process for imaging diagnosis quality measurement.

Improving the Efficacy of the Data Entry Process for Clinical Research With a Natural Language Processing-Driven Medical Information Extraction System: Quantitative Field Research.

BACKGROUND: The growing interest in observational trials using patient data from electronic medical records poses challenges to both efficiency and quality of clinical data collection and management. Even with the help of electronic data capture systems and electronic case report forms (eCRFs), the manual data entry process followed by chart review is still time consuming. OBJECTIVE: To facilitate the data entry process, we developed a natural language processing-driven medical information extraction system (NLP-MIES) based on the i2b2 reference standard. We aimed to evaluate whether the NLP-MIES-based eCRF application could improve the accuracy and efficiency of the data entry process. METHODS: We conducted a randomized and controlled field experiment, and 24 eligible participants were recruited (12 for the manual group and 12 for NLP-MIES-supported group). We simulated the real-world eCRF completion process using our system and compared the performance of data entry on two research topics, pediatric congenital heart disease and pneumonia. RESULTS: For the congenital heart disease condition, the NLP-MIES-supported group increased accuracy by 15% (95% CI 4%-120%, P=.03) and reduced elapsed time by 33% (95% CI 22%-42%, P<.001) compared with the manual group. For the pneumonia condition, the NLP-MIES-supported group increased accuracy by 18% (95% CI 6%-32%, P=.008) and reduced elapsed time by 31% (95% CI 19%-41%, P<.001). CONCLUSIONS: Our system could improve both the accuracy and efficiency of the data entry process.

Development of a Consumer Health Vocabulary by Mining Health Forum Texts Based on Word Embedding: Semiautomatic Approach.

BACKGROUND: The vocabulary gap between consumers and professionals in the medical domain hinders information seeking and communication. Consumer health vocabularies have been developed to aid such informatics applications. This purpose is best served if the vocabulary evolves with consumers' language. OBJECTIVE: Our objective is to develop a method for identifying and adding new terms to consumer health vocabularies, so that it can keep up with the constantly evolving medical knowledge and language use. METHODS: In this paper, we propose a consumer health term-finding framework based on a distributed word vector space model. We first learned word vectors from a large-scale text corpus and then adopted a supervised method with existing consumer health vocabularies for learning vector representation of words, which can provide additional supervised fine tuning after unsupervised word embedding learning. With a fine-tuned word vector space, we identified pairs of professional terms and their consumer variants by their semantic distance in the vector space. A subsequent manual review of the extracted and labeled pairs of entities was conducted to validate the results generated by the proposed approach. The results were evaluated using mean reciprocal rank (MRR). RESULTS: Manual evaluation showed that it is feasible to identify alternative medical concepts by using professional or consumer concepts as queries in the word vector space without fine tuning, but the results are more promising in the final fine-tuned word vector space. The MRR values indicated that on an average, a professional or consumer concept is about 14th closest to its counterpart in the word vector space without fine tuning, and the MRR in the final fine-tuned word vector space is 8. Furthermore, the results demonstrate that our method can collect abbreviations and common typos frequently used by consumers. CONCLUSIONS: By integrating a large amount of text information and existing consumer health vocabularies, our method outperformed several baseline ranking methods and is effective for generating a list of candidate terms for human review during consumer health vocabulary development.

A cascaded approach for Chinese clinical text de-identification with less annotation effort.

With rapid adoption of Electronic Health Records (EHR) in China, an increasing amount of clinical data has been available to support clinical research. Clinical data secondary use usually requires de-identification of personal information to protect patient privacy. Since manually de-identification of free clinical text requires significant amount of human work, developing an automated de-identification system is necessary. While there are many de-identification systems available for English clinical text, designing a de-identification system for Chinese clinical text faces many challenges such as unavailability of necessary lexical resources and sparsity of patient health information (PHI) in Chinese clinical text. In this paper, we designed a de-identification pipeline taking advantage of both rule-based and machine learning techniques. Our method, in particular, can effectively construct a data set with dense PHI information, which saves annotation time significantly for subsequent supervised learning. We experiment on a dataset of 3000 heterogeneous clinical documents to evaluate the annotation cost and the de-identification performance. Our approach can increase the efficiency of the annotation effort by over 60% while reaching performance as high as over 90% measured by F score. We demonstrate that combing rule-based and machine learning is an effective way to reduce the annotation cost and achieve high performance in Chinese clinical text de-identification task.

MicroRNA-543 suppresses colorectal cancer growth and metastasis by targeting KRAS, MTA1 and HMGA2.

miR-543 has been implicated as having a critical role in the development of breast cancer, endometrial cancer and hepatocellular carcinoma. However, the exact clinical significance and biological functions of miR-543 in colorectal cancer (CRC) remain unclear. Here, we found that miR-543 expression significantly downregulated in tumors from patients with CRC, APCMin mice and a mouse model of colitis-associated colon cancer. miR-543 level was inversely correlated with the metastatic status of patients with CRC and the metastatic potential of CRC cell lines. Moreover, ectopic expression of miR-543 inhibited the proliferation and metastasis of CRC cells in vitro and in vivo by targeting KRAS, MTA1 and HMGA2. Conversely, miR-543 knockdown promoted the proliferation, migration and invasion of CRC cells in vitro and augmented tumor growth and metastasis in vivo. Furthermore, we found that miR-543 expression was negatively correlated with the levels of KRAS, MTA1 and HMGA2 in clinical samples. Collectively, these data show that miR-543 inhibits the proliferation and metastasis of CRC cells by targeting KRAS, MTA1 and HMGA2. Our study highlights a pivotal role for miR-543 as a suppressor in the regulation of CRC growth and metastasis and suggests that miR-543 may serve as a novel diagnostic and prognostic biomarker for CRC metastasis.

Prediction of black box warning by mining patterns of Convergent Focus Shift in clinical trial study populations using linked public data.

OBJECTIVE: To link public data resources for predicting post-marketing drug safety label changes by analyzing the Convergent Focus Shift patterns among drug testing trials. METHODS: We identified 256 top-selling prescription drugs between 2003 and 2013 and divided them into 83 BBW drugs (drugs with at least one black box warning label) and 173 ROBUST drugs (drugs without any black box warning label) based on their FDA black box warning (BBW) records. We retrieved 7499 clinical trials that each had at least one of these drugs for intervention from the ClinicalTrials.gov. We stratified all the trials by pre-marketing or post-marketing status, study phase, and study start date. For each trial, we retrieved drug and disease concepts from clinical trial summaries to model its study population using medParser and SNOMED-CT. Convergent Focus Shift (CFS) pattern was calculated and used to assess the temporal changes in study populations from pre-marketing to post-marketing trials for each drug. Then we selected 68 candidate drugs, 18 with BBW warning and 50 without, that each had at least nine pre-marketing trials and nine post-marketing trials for predictive modeling. A random forest predictive model was developed to predict BBW acquisition incidents based on CFS patterns among these drugs. Pre- and post-marketing trials of BBW and ROBUST drugs were compared to look for their differences in CFS patterns. RESULTS: Among the 18 BBW drugs, we consistently observed that the post-marketing trials focused more on recruiting patients with medical conditions previously unconsidered in the pre-marketing trials. In contrast, among the 50 ROBUST drugs, the post-marketing trials involved a variety of medications for testing their associations with target intervention(s). We found it feasible to predict BBW acquisitions using different CFS patterns between the two groups of drugs. Our random forest predictor achieved an AUC of 0.77. We also demonstrated the feasibility of the predictor for identifying long-term BBW acquisition events without compromising prediction accuracy. CONCLUSIONS: This study contributes a method for post-marketing pharmacovigilance using Convergent Focus Shift (CFS) patterns in clinical trial study populations mined from linked public data resources. These signals are otherwise unavailable from individual data resources. We demonstrated the added value of linked public data and the feasibility of integrating ClinicalTrials.gov summaries and drug safety labels for post-marketing surveillance. Future research is needed to ensure better accessibility and linkage of heterogeneous drug safety data for efficient pharmacovigilance.

IDENTIFICATION OF QUESTIONABLE EXCLUSION CRITERIA IN MENTAL DISORDER CLINICAL TRIALS USING A MEDICAL ENCYCLOPEDIA.

Precision medicine requires precise evidence-based practice and precise definition of the patients included in clinical studies for evidence generalization. Clinical research exclusion criteria define confounder patient characteristics for exclusion from a study. However, unnecessary exclusion criteria can weaken patient representativeness of study designs and generalizability of study results. This paper presents a method for identifying questionable exclusion criteria for 38 mental disorders. We extracted common eligibility features (CEFs) from all trials on these disorders from ClinicalTrials.gov. Network Analysis showed scale-free property of the CEF network, indicating uneven usage frequencies among CEFs. By comparing these CEFs' term frequencies in clinical trials' exclusion criteria and in the PubMed Medical Encyclopedia for matching conditions, we identified unjustified potential overuse of exclusion CEFs in mental disorder trials. Then we discussed the limitations in current exclusion criteria designs and made recommendations for achieving more patient-centered exclusion criteria definitions.